Introduction to Machine Learning

Introduction to ML

Machine learning (ML) is an advanced form of Artificial Intelligence (AI) that uses data to create models and make predictions. It has the ability to automate complex tasks such as facial recognition and natural language processing, providing businesses and individuals with powerful tools for decision-making.

Other applications of ML include computer vision, recommendation systems, fraud detection and more. ML has become increasingly popular in recent months due to its ability to create insights from large datasets, thus improving efficiency and accuracy of processes. As technology continues to evolve, machine learning will play an essential role in many aspects of our lives.

Remember!  Machine learning is just a "thing labeler".  

--------------------

These computer programs use artificial intelligence to look for patterns in data without human instruction. 

• predictive algorithms
• pattern recognition

How computer algorithms make predictions:
https://www.youtube.com/watch?v=WvhOtirThZY

Machine learning is a subset of artificial intelligence that automates data-driven predictions and decisions. It works by studying patterns in the data provided and using that information to detect certain relationships or trends. Machine learning utilizes algorithms to enable computers to learn from the data without requiring instructions on what data should be analyzed. Machine learning algorithms access large datasets to identify insights or patterns, then adjust their parameters according to the feedback they receive as part of the learning process. With each pass of the algorithm, it can gain insight into the patterns established by its data set, meaning it can improve decisions over time as more data is processed.

• AI / Models / ML / Neural Networks
• Machine Learning is a "thing labeler"
• You feed examples into the system
• The ML algorithm then builds "recipe"

• Machine Learning's job is to succeed on new data situations
• If old data, just look it up
• If no pattern in data, nothing can help 
• If patterns that can be found and used

• Which models do we trust?
  • Support Vector Classifier (SVM) or Decision Tree
• Which works on the new stuff?
• Look at accuracy

• Math, lots of math
• Various algorithms to use
• Linear Regression
•  

• Attitude for machine learning is to just continually test
• Just go for it!
• Line = Intercept + Slope * Weight
• Want information to do better
• Error = point - line 
• RMSE: root mean squared error - to minimize error
• Optimization algorithm

• Need more information
• Need better information
• Try various features